Browse
Submit Data
Databases
API
Help

Dataset Information

13 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Combined molecular dynamics and neural network method for predicting protein antifreeze activity.

ABSTRACT: Antifreeze proteins (AFPs) are a diverse class of proteins that depress the kinetically observable freezing point of water. AFPs have been of scientific interest for decades, but the lack of an accurate model for predicting AFP activity has hindered the logical design of novel antifreeze systems. To address this, we perform molecular dynamics simulation for a collection of well-studied AFPs. By analyzing both the dynamic behavior of water near the protein surface and the geometric structure of the protein, we introduce a method that automatically detects the ice binding face of AFPs. From these data, we construct a simple neural network that is capable of quantitatively predicting experimentally observed thermal hysteresis from a trio of relevant physical variables. The model's accuracy is tested against data for 17 known AFPs and 5 non-AFP controls.

SUBMITTER: Kozuch DJ

PROVIDER: S-EPMC6310784 | biostudies-literature | 2018 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Publications

Combined molecular dynamics and neural network method for predicting protein antifreeze activity.

Kozuch Daniel J DJ Stillinger Frank H FH Debenedetti Pablo G PG

Proceedings of the National Academy of Sciences of the United States of America 20181207 52

Antifreeze proteins (AFPs) are a diverse class of proteins that depress the kinetically observable freezing point of water. AFPs have been of scientific interest for decades, but the lack of an accurate model for predicting AFP activity has hindered the logical design of novel antifreeze systems. To address this, we perform molecular dynamics simulation for a collection of well-studied AFPs. By analyzing both the dynamic behavior of water near the protein surface and the geometric structure of t ...[more]

PMID: 30530650

Similar Datasets

The biological function of an insect antifreeze protein simulated by molecular dynamics.

Project description:Antifreeze proteins (AFPs) protect certain cold-adapted organisms from freezing to death by selectively adsorbing to internal ice crystals and inhibiting ice propagation. The molecular details of AFP adsorption-inhibition is uncertain but is proposed to involve the Gibbs-Thomson effect. Here we show by using unbiased molecular dynamics simulations a protein structure-function mechanism for the spruce budworm Choristoneura fumiferana AFP, including stereo-specific binding and consequential melting and freezing inhibition. The protein binds indirectly to the prism ice face through a linear array of ordered water molecules that are structurally distinct from the ice. Mutation of the ice binding surface disrupts water-ordering and abolishes activity. The adsorption is virtually irreversible, and we confirm the ice growth inhibition is consistent with the Gibbs-Thomson law.

| S-EPMC4442126 | biostudies-literature

Dual Convolutional Neural Network Based Method for Predicting Disease-Related miRNAs.

Project description:Identification of disease-related microRNAs (disease miRNAs) is helpful for understanding and exploring the etiology and pathogenesis of diseases. Most of recent methods predict disease miRNAs by integrating the similarities and associations of miRNAs and diseases. However, these methods fail to learn the deep features of the miRNA similarities, the disease similarities, and the miRNA?disease associations. We propose a dual convolutional neural network-based method for predicting candidate disease miRNAs and refer to it as CNNDMP. CNNDMP not only exploits the similarities and associations of miRNAs and diseases, but also captures the topology structures of the miRNA and disease networks. An embedding layer is constructed by combining the biological premises about the miRNA?disease associations. A new framework based on the dual convolutional neural network is presented for extracting the deep feature representation of associations. The left part of the framework focuses on integrating the original similarities and associations of miRNAs and diseases. The novel miRNA and disease similarities which contain the topology structures are obtained by random walks on the miRNA and disease networks, and their deep features are learned by the right part of the framework. CNNDMP achieves the superior prediction performance than several state-of-the-art methods during the cross-validation process. Case studies on breast cancer, colorectal cancer and lung cancer further demonstrate CNNDMP's powerful ability of discovering potential disease miRNAs.

| S-EPMC6321160 | biostudies-literature

Graph Convolutional Network and Convolutional Neural Network Based Method for Predicting lncRNA-Disease Associations.

Project description:Aberrant expressions of long non-coding RNAs (lncRNAs) are often associated with diseases and identification of disease-related lncRNAs is helpful for elucidating complex pathogenesis. Recent methods for predicting associations between lncRNAs and diseases integrate their pertinent heterogeneous data. However, they failed to deeply integrate topological information of heterogeneous network comprising lncRNAs, diseases, and miRNAs. We proposed a novel method based on the graph convolutional network and convolutional neural network, referred to as GCNLDA, to infer disease-related lncRNA candidates. The heterogeneous network containing the lncRNA, disease, and miRNA nodes, is constructed firstly. The embedding matrix of a lncRNA-disease node pair was constructed according to various biological premises about lncRNAs, diseases, and miRNAs. A new framework based on a graph convolutional network and a convolutional neural network was developed to learn network and local representations of the lncRNA-disease pair. On the left side of the framework, the autoencoder based on graph convolution deeply integrated topological information within the heterogeneous lncRNA-disease-miRNA network. Moreover, as different node features have discriminative contributions to the association prediction, an attention mechanism at node feature level is constructed. The left side learnt the network representation of the lncRNA-disease pair. The convolutional neural networks on the right side of the framework learnt the local representation of the lncRNA-disease pair by focusing on the similarities, associations, and interactions that are only related to the pair. Compared to several state-of-the-art prediction methods, GCNLDA had superior performance. Case studies on stomach cancer, osteosarcoma, and lung cancer confirmed that GCNLDA effectively discovers the potential lncRNA-disease associations.

| S-EPMC6769579 | biostudies-literature

Convolutional neural network architectures for predicting DNA-protein binding.

Project description:MotivationConvolutional neural networks (CNN) have outperformed conventional methods in modeling the sequence specificity of DNA-protein binding. Yet inappropriate CNN architectures can yield poorer performance than simpler models. Thus an in-depth understanding of how to match CNN architecture to a given task is needed to fully harness the power of CNNs for computational biology applications.ResultsWe present a systematic exploration of CNN architectures for predicting DNA sequence binding using a large compendium of transcription factor datasets. We identify the best-performing architectures by varying CNN width, depth and pooling designs. We find that adding convolutional kernels to a network is important for motif-based tasks. We show the benefits of CNNs in learning rich higher-order sequence features, such as secondary motifs and local sequence context, by comparing network performance on multiple modeling tasks ranging in difficulty. We also demonstrate how careful construction of sequence benchmark datasets, using approaches that control potentially confounding effects like positional or motif strength bias, is critical in making fair comparisons between competing methods. We explore how to establish the sufficiency of training data for these learning tasks, and we have created a flexible cloud-based framework that permits the rapid exploration of alternative neural network architectures for problems in computational biology.Availability and implementationAll the models analyzed are available at http://cnn.csail.mit.eduContactgifford@mit.eduSupplementary informationSupplementary data are available at Bioinformatics online.

| S-EPMC4908339 | biostudies-literature

Increased flexibility decreases antifreeze protein activity.

Project description:Antifreeze proteins protect several cold-blooded organisms from subzero environments by preventing death from freezing. The Type I antifreeze protein (AFP) isoform from Pseudopleuronectes americanus, named HPLC6, is a 37-residue protein that is a single ?-helix. Mutational analysis of the protein showed that its alanine-rich face is important for binding to and inhibiting the growth of macromolecular ice. Almost all structural studies of HPLC6 involve the use of chemically synthesized protein as it requires a native N-terminal aspartate and an amidated C-terminus for full activity. Here, we examine the role of C-terminal amide and C-terminal arginine side chain in the activity, structure, and dynamics of nonamidated Arg37 HPLC6, nonamidated HPLC6 Ala37, amidated HPLC6 Ala37, and fully native HPLC6 using a recombinant bacterial system. The thermal hysteresis (TH) activities of the nonamidated mutants are 35% lower compared with amidated proteins, but analysis of the NMR data and circular dichroism spectra shows that they are all still ?-helical. Relaxation data from the two nonamidated mutants indicate that the C-terminal residues are considerably more flexible than the rest of the protein because of the loss of the amide group, whereas the amidated Ala37 mutant has a C-terminus that is as rigid as the wild-type protein and has high TH activity. We propose that an increase in flexibility of the AFP causes it to lose activity because its dynamic nature prevents it from binding strongly to the ice surface.

| S-EPMC3009403 | biostudies-literature

Structural basis of antifreeze activity of a bacterial multi-domain antifreeze protein.

Project description:Antifreeze proteins (AFPs) enhance the survival of organisms inhabiting cold environments by affecting the formation and/or structure of ice. We report the crystal structure of the first multi-domain AFP that has been characterized. The two ice binding domains are structurally similar. Each consists of an irregular ?-helix with a triangular cross-section and a long ?-helix that runs parallel on one side of the ?-helix. Both domains are stabilized by hydrophobic interactions. A flat plane on the same face of each domain's ?-helix was identified as the ice binding site. Mutating any of the smaller residues on the ice binding site to bulkier ones decreased the antifreeze activity. The bulky side chain of Leu174 in domain A sterically hinders the binding of water molecules to the protein backbone, partially explaining why antifreeze activity by domain A is inferior to that of domain B. Our data provide a molecular basis for understanding differences in antifreeze activity between the two domains of this protein and general insight on how structural differences in the ice-binding sites affect the activity of AFPs.

| S-EPMC5673226 | biostudies-literature

Perturbation of long-range water dynamics as the mechanism for the antifreeze activity of antifreeze glycoprotein.

Project description:Very little is known about the mechanism of antifreeze action of antifreeze glycoproteins (AFGPs) present in Antarctic teleost fish. Recent NMR and CD studies assisted with total synthesis of synthetic AFGP variants have provided insight into the structure of short AFGP glycopeptides, though the observations did not yield information on the antifreeze mechanism of action. In this study, we use Hamiltonian replica exchange (HREX) molecular dynamics simulations to probe the structure and surrounding aqueous environments of both the natural (AFGP8) and synthetic (s-AFGP4) AFGPs. AFGPs can adopt both amphiphilic and pseudoamphiphilic conformations, the preference of which is related to the proline content of the peptide. The arrangement of carbohydrates allows the hydroxyl groups on terminal galactose units to form stable water bridges which in turn influence the hydrogen-bond network, structure, and dynamics of the surrounding solvent. Interestingly, these local effects lead to the perturbation of the tetrahedral environment for water molecules in hydration layers far (10.0-12.0 Å) from the AFGPs. This structure-induced alteration of long-range hydration dynamics is proposed to be the major contributor to antifreeze activity, a conclusion that is in line with terahertz spectroscopy experiments. The detailed structure-mechanism correlation provided in this study could lead to the design of better synthetic AFGP variants.

| S-EPMC4191590 | biostudies-literature

ChloroP, a neural network-based method for predicting chloroplast transit peptides and their cleavage sites.

Project description:We present a neural network based method (ChloroP) for identifying chloroplast transit peptides and their cleavage sites. Using cross-validation, 88% of the sequences in our homology reduced training set were correctly classified as transit peptides or nontransit peptides. This performance level is well above that of the publicly available chloroplast localization predictor PSORT. Cleavage sites are predicted using a scoring matrix derived by an automatic motif-finding algorithm. Approximately 60% of the known cleavage sites in our sequence collection were predicted to within +/-2 residues from the cleavage sites given in SWISS-PROT. An analysis of 715 Arabidopsis thaliana sequences from SWISS-PROT suggests that the ChloroP method should be useful for the identification of putative transit peptides in genome-wide sequence data. The ChloroP predictor is available as a web-server at http://www.cbs.dtu.dk/services/ChloroP/.

| S-EPMC2144330 | biostudies-other

Chromatin Interaction Neural Network (ChINN): A machine learning-based method for predicting chromatin interactions from DNA sequences

Project description:Chromatin interactions play important roles in regulating gene expression. However, the availability of genome-wide chromatin interaction data is limited. Various computational methods have been developed to predict chromatin interactions. Most of these methods rely on large collections of ChIP-Seq/RNA-Seq/DNase-Seq datasets and predict only enhancer-promoter interactions. Some of the ‘state-of-the-art’ methods have poor experimental designs, leading to over-exaggerated performances and misleading conclusions. Here we developed a computational method, Chromatin Interaction Neural Network (CHINN), to predict chromatin interactions between open chromatin regions by using only DNA sequences of the interacting open chromatin regions. CHINN is able to predict CTCF-, RNA polymerase II- and HiC-associated chromatin interactions between open chromatin regions. CHINN also shows good across-sample performances and captures various sequence features that are predictive of chromatin interactions. We applied CHINN to 90 chronic lymphocytic leukemia (CLL) samples and detected systematic differences in the chromatin interactome between IGVH-mutated and IGVH-unmutated CLL samples.

2021-07-09 | GSE163896 | GEO

Predicting improved protein conformations with a temporal deep recurrent neural network.

Project description:Accurate protein structure prediction from amino acid sequence is still an unsolved problem. The most reliable methods centre on template based modelling. However, the accuracy of these models entirely depends on the availability of experimentally resolved homologous template structures. In order to generate more accurate models, extensive physics based molecular dynamics (MD) refinement simulations are performed to sample many different conformations to find improved conformational states. In this study, we propose a deep recurrent network model, called DeepTrajectory, that is able to identify these improved conformational states, with high precision, from a variety of different MD based sampling protocols. The proposed model learns the temporal patterns of features computed from MD trajectory data in order to classify whether each recorded simulation snapshot is an improved quality conformational state, decreased quality conformational state or whether there is no perceivable change in state with respect to the starting conformation. The model was trained and tested on 904 trajectories from 42 different protein systems with a cumulative number of more than 1.7 million snapshots. We show that our model outperforms other state of the art machine-learning algorithms that do not consider temporal dependencies. To our knowledge, DeepTrajectory is the first implementation of a time-dependent deep-learning protocol that is re-trainable and able to adapt to any new MD based sampling procedure, thereby demonstrating how a neural network can be used to learn the latter part of the protein folding funnel.

| S-EPMC6122789 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data